Manual human machine interface operation system and method thereof
AssigneeAcer Incorporated
InventorsCHUNG-CHENG LOU, JING-WEI WANG
Life of this patent
Estimating the term…
Abstract
A manual human machine interface operation system and method thereof are disclosed. In embodiment, this manual human machine interface operation system extracts user's arm image and palm image from the images capture by at least two cameras, and then calculates user's arm coordinate, so that user can select the object shown on the human machine interface by manually using his/her arm. The system then recognizes a hand posture according to the palm image and determines an instruction mapped to this hand posture. This instruction is then performed on the selected object. In embodiment, the hand posture can be a pointing posture, grab posture or a release posture.
Claims12
A manual human machine interface operation system, comprising:
- a display unit;
- a data processing unit, generating a human machine interface with multiple objects, and each of said objects containing a depth parameter, and said data processing unit controlling said display unit to display said human machine interface;
- multiple image capture units capturing multiple hand images and each of said images capture units having multiple intrinsic parameters and multiple extrinsic parameters;
- an image analysis unit, analyzing said multiple hand images to obtain multiple arm images and multiple palm images;
- a coordinate calculation unit, according to said arm images and intrinsic parameters and extrinsic parameters of each of image capture units, calculating arm feature points, and calculating an arm extension line and an arm movement according to said arm feature points;
- and
- a hand posture recognition unit, recognizing a hand posture according to said palm images;
- wherein said data processing unit is operable to, according to said arm extension line, said arm movement and said depth parameters of said objects, determine a selected object from said objects, and determine an instruction corresponding to said hand posture, and perform said instruction on said selected object.
A method of operating a manual human machine interface with multiple objects, and each of said objects containing a depth parameter, said method comprising steps of:
- using multiple image capture units to capture multiple hand images, and each of said image capture units having multiple intrinsic parameters and multiple extrinsic parameters;
- analyzing said multiple hand images to obtain multiple arm images and multiple palm images;
- according to said arm images and intrinsic parameters and extrinsic parameters of each of image capture units, calculating arm feature points, and calculating an arm extension line and an arm movement according to said arm feature points;
- according to said arm extension line, said arm movement and said depth parameters of said objects, determine a selected object from said objects;
- recognizing a hand posture according to said palm images;
- and
- determining an instruction corresponding to said hand posture and performing said instruction on said selected object.
Dependencies are inferred from the claim text.